Answering Open-Domain Questions of Varying Reasoning Steps from Text
This work addresses the challenge of scalable and flexible question answering for real-world applications by eliminating dependencies on prior knowledge of reasoning complexity, though it is incremental in improving upon existing methods for open-domain QA.
The authors tackled the problem of answering open-domain questions requiring varying numbers of retrieval steps from text, developing a unified system that uses a single multi-task transformer model to iteratively perform retrieval, reranking, and answer prediction without relying on assumptions like fixed step counts or structured metadata. They introduced a new benchmark, BeerQA, combining existing datasets with 530 new three-step questions, and showed competitive performance on both existing and new benchmarks.
We develop a unified system to answer directly from text open-domain questions that may require a varying number of retrieval steps. We employ a single multi-task transformer model to perform all the necessary subtasks -- retrieving supporting facts, reranking them, and predicting the answer from all retrieved documents -- in an iterative fashion. We avoid crucial assumptions of previous work that do not transfer well to real-world settings, including exploiting knowledge of the fixed number of retrieval steps required to answer each question or using structured metadata like knowledge bases or web links that have limited availability. Instead, we design a system that can answer open-domain questions on any text collection without prior knowledge of reasoning complexity. To emulate this setting, we construct a new benchmark, called BeerQA, by combining existing one- and two-step datasets with a new collection of 530 questions that require three Wikipedia pages to answer, unifying Wikipedia corpora versions in the process. We show that our model demonstrates competitive performance on both existing benchmarks and this new benchmark. We make the new benchmark available at https://beerqa.github.io/.